AI RESEARCH
FreeStreamGS: Online Feed-forward 3D Gaussian Splatting from Unposed Streaming Inputs
arXiv CS.CV
•
ArXi:2606.03254v1 Announce Type: new Feed-forward 3D Gaussian Splatting (3DGS) allows efficient and high-fidelity novel view synthesis (NVS) from an offline recorded image sequence. However, achieving online NVS from streaming and unposed image inputs remains challenging. Although online feed-forward geometric estimation methods have been proposed for streaming depth and point cloud recovery, they cannot be adapted to NVS due to severe rendering artifacts.